• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.93.4-93
• /
• 2001

Based on input and output data pairs of nonlinear systems, this paper proposes a simple and effective Just-In-Time (JIT) method, called Direct JIT Control, for nonlinear control design. It uses an inverse model of controlled plant to compute an initial control action, and then adapts the initial control action by adding a fine-tuning control action, depended on the errors between the real outputs and the expected reference signals. Meanwhile, the proposed JIT method accomplishes the adaptation of the inverse model just simply by means of the refreshment of input and output data pairs. In addition, the JIT modeling technique guarantees this method to obtain an approximate inverse model of the controlled nonlinear plant in the neighborhood of a query. Based on a ...

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1995년도 추계학술대회 학술발표 논문집
• /
• pp.59-70
• /
• 1995

Output performance improvement using fuzzy logic to the conventional control scheme for a magnetic levitation system is presented in this paper, Adverse characteristics of nonlinearity, unstability, system parameter variation, etc, in the levitation system are partially overcome by the general fuzzy control action. Using a PD type compensator, a coarse framework of output performance is provided to the levitation system. Then a fine regulation to the output performance requirement is obtained by the natural description of the control action in the form of fuzzy logic controller. This control action soothes the adverse characteristics of the levitation system. In this way a better output performance can be obtained in a real time experiment.

• 생명과학회지
• /
• 제6권2호
• /
• pp.104-110
• /
• 1996

The present study was conducted to elucidate the functional property of tea extract obtained from tea extracts, semi-fermented tea(oolong tea) and fermented tea(black tea). Tea extracts exhibited remarkable nitrite-scavenging actions, and the action increased with the increased of the amount of tea extracts. The nitrite-scavenging actionof tea extracts showed pH dependent, highest at pH 1.2 and lowest at pH6.0. The nitrite-scavenging rate in tea extracts/amine/nitrite systems proved to be faster than that in amine/nitrite systems. To screen the nitrite-scavenging factors, tea extracts were fractionated into water-soluble, methanol-soluble, methanol-precipitate and crude catechin fraction. Among these fractions of tea extracts, the crude catechin fraction possessed greater nitrite-scavenging action than the other fractions. The nitrite-scavenging action of tea extracts increased with the contents of total phenols and an absorbance at 280nm, nitrite-scavenging factors were supposed to be and catechins in tea polyphenol compounds.

• 한국지능시스템학회논문지
• /
• 제7권5호
• /
• pp.60-66
• /
• 1997

This paper presents a fuzzy inference-based reinforcement learning algorithm of dynamci recurrent neural networks, which is very similar to the psychological learning method of higher animals. By useing the fuzzy inference technique the linguistic and concetional expressions have an effect on the controller's action indirectly, which is shown in human's behavior. The intervlas of fuzzy membership functions are found optimally by genetic algorithms. And using recurrent neural networks composed of dynamic neurons as action-generation networks, past state as well as current state is considered to make an action in dynamical environment. We show the validity of the proposed learning algorithm by applying it to the inverted pendulum control problem.

• 품질경영학회지
• /
• 제47권3호
• /
• pp.571-582
• /
• 2019

Purpose: To develop a risk metric for failure cause that can help determine the action priority of each failure cause in FMEA considering time sequence of cause- failure- detection. Methods: Assuming a quadratic loss function the unfulfilled mission period, a risk metric is obtained by deriving the failure time distribution. Results: The proposed risk metric has some reasonable properties for evaluating risk accompanied with a failure cause. Conclusion: The study may be applied to determining action priorities among all the failure causes in the FMEA sheet, requiring further studies for general situation of failure process.

• 대한조선학회논문집
• /
• 제56권1호
• /
• pp.58-65
• /
• 2019

The stability, reliability and efficiency of a smart ship are important issues as the interest in an autonomous ship has recently been high. An automatic collision avoidance system is an essential function of an autonomous ship. This system detects the possibility of collision and automatically takes avoidance actions in consideration of economy and safety. In order to construct an automatic collision avoidance system using reinforcement learning, in this work, the sequential decision problem of ship collision is mathematically formulated through a Markov Decision Process (MDP). A reinforcement learning environment is constructed based on the ship maneuvering equations, and then the three key components (state, action, and reward) of MDP are defined. The state uses parameters of the relationship between own-ship and target-ship, the action is the vertical distance away from the target course, and the reward is defined as a function considering safety and economics. In order to solve the sequential decision problem, the Deep Deterministic Policy Gradient (DDPG) algorithm which can express continuous action space and search an optimal action policy is utilized. The collision avoidance system is then tested assuming the $90^{\circ}$intersection encounter situation and yields a satisfactory result.

• Journal of Information Processing Systems
• /
• 제9권2호
• /
• pp.259-270
• /
• 2013

A speaker's intentions can be represented by domain actions (domain-independent speech act and domain-dependent concept sequence pairs). Therefore, it is essential that domain actions be determined when implementing dialogue systems because a dialogue system should determine users' intentions from their utterances and should create counterpart intentions to the users' intentions. In this paper, a neural network model is proposed for classifying a user's domain actions and planning a system's domain actions. An integrated neural network model is proposed for simultaneously determining user and system domain actions using the same framework. The proposed model performed better than previous non-integrated models in an experiment using a goal-oriented dialogue corpus. This result shows that the proposed integration method contributes to improving domain action determination performance.

• Journal of Mechanical Science and Technology
• /
• 제17권3호
• /
• pp.321-328
• /
• 2003

The elongation of contact length on the line of action is considered with particular reference for roll forming of gears, and for dynamic behavior of the tooth in meshing. However there is no paper that discuss the elongation of contact length in the load meshing of gears. Based on our investigation, the contact length on the line of action elongates more than the kinematically calculated value. In rolling, as the tool approaches the workpiece, the center distance of the gears decreases by a small amount. But, the elongation of contact length is sensitive. Therefore, the contact point on the line of action is difficult to be determined, which complicates the tooth analysis. In this study, the exact relation between the elongation of contact length and the tooth space over the recess or before the approach are revealed by experiments and kinematic theory. This analytical result applies not only for rolling, but also for the single flank meshing which is done under constant center distance.

• Journal of Electrical Engineering and Technology
• /
• 제10권4호
• /
• pp.1851-1863
• /
• 2015

– In the paper, to handle the problem of traditional bag-of-features model ignoring the spatial relationship of local features in human action recognition, we proposed a Multiscale Spatial Position Coding under Locality Constraint method. Specifically, to describe this spatial relationship, we proposed a mixed feature combining motion feature and multi-spatial-scale configuration. To utilize temporal information between features, sub spatial-temporal-volumes are built. Next, the pooled features of sub-STVs are obtained via max-pooling method. In classification stage, the Locality-Constrained Group Sparse Representation is adopted to utilize the intrinsic group information of the sub-STV features. The experimental results on the KTH, Weizmann, and UCF sports datasets show that our action recognition system outperforms the classical local ST feature-based recognition systems published recently.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2027-2032
• /
• 2003

For action selection as well as learning, simple associations between stimulus and response have been employed in most of literatures. But, for a successful task accomplishment, it is required that an animat can learn and express behavioral sequences. In this paper, we propose a novel action-selection-mechanism to deal with sequential behaviors. For this, we define behavioral motivation as a primitive node for action selection, and then hierarchically construct a network with behavioral motivations. The vertical path of the network represents behavioral sequences. Here, such a tree for our proposed ASM can be newly generated and/or updated, whenever a new sequential behaviors is learned. To show the validity of our proposed ASM, three 2-D grid world simulations will be illustrated.